Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1848. Min Range: -3.1848
Max Act: 3.1848. Min Act: -0.1700
Data Index: 4450720 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1848. Min Range: -3.1848
Max Act: 3.0903. Min Act: -0.1700
Data Index: 452363 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1848. Min Range: -3.1848
Max Act: 3.0430. Min Act: -0.1700
Data Index: 3414649 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9956. Min Act: -0.1700
Data Index: 5064591 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9798. Min Act: -0.1700
Data Index: 7802855 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9640. Min Act: -0.1700
Data Index: 2007781 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9798. Min Act: -0.1700
Data Index: 745328 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9640. Min Act: -0.1700
Data Index: 4993176 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9640. Min Act: -0.1700
Data Index: 2228191 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9640. Min Act: -0.1700
Data Index: 6188652 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9323. Min Act: -0.1700
Data Index: 195762 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9165. Min Act: -0.1700
Data Index: 8048029 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9165. Min Act: -0.1700
Data Index: 1788956 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9323. Min Act: -0.1700
Data Index: 2357822 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9165. Min Act: -0.1700
Data Index: 7767438 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9006. Min Act: -0.1700
Data Index: 3398412 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.9165. Min Act: -0.1700
Data Index: 2865880 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.8689. Min Act: -0.1700
Data Index: 8249934 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.8689. Min Act: -0.1700
Data Index: 4880718 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1848. Min Range: -3.1848
Max Act: 2.8848. Min Act: -0.1700
Data Index: 4964263 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19